© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44040
    Prev
    Next
    INDEX
    Explanations

    alligator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Duchess
    -0.71
     Wills
    -0.71
     Alligator
    -0.69
     alligator
    -0.69
    RegistryLite
    -0.64
     duchess
    -0.55
    untung
    -0.52
    __':
    -0.51
    lej
    -0.46
    puh
    -0.46
    POSITIVE LOGITS
     propOrder
    0.79
    Javadoc
    0.71
     linkovi
    0.68
    HasAnnotation
    0.67
    #+#
    0.66
     nakalista
    0.66
     iprot
    0.65
     EClass
    0.65
     فريبيس
    0.64
    titleMargin
    0.64
    Activations Density 0.317%

    No Known Activations